© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 125
    Prev
    Next
    INDEX
    Explanations

    æĪĸ

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /navbar
    -0.30
    /effects
    -0.28
    /sidebar
    -0.28
    /animations
    -0.27
     +=↵
    -0.27
     AndAlso
    -0.24
    ï¼ģ",
    -0.24
    /respond
    -0.24
    ï¼ģ');↵
    -0.24
    /Runtime
    -0.23
    POSITIVE LOGITS
    æĪĸ
    1.47
     or
    1.44
    æĪĸèĢħ
    1.38
    æĪĸæĺ¯
    1.32
    æĪĸèĢħæĺ¯
    1.22
     æĪĸ
    1.20
     или
    1.16
    æĪĸåħ¶ä»ĸ
    1.16
    æĪĸå¤ļ
    1.01
    æĪĸèĢħåħ¶ä»ĸ
    1.00
    Activations Density 11.127%

    No Known Activations